R Notebook

Utility functions

dataset_name != all_files[file_id]

[1] TRUE

Path variables

# dataset base path
base_path = "/Users/lana/Desktop/prgm/CSL/FLR_contest/data/"

Bird data. Selected: 0, 1, 4, 7, 13

dataset_dir = paste(base_path, "real_life/Annotated20GPS20tracking20data/data/", sep = "")
output_dir = "real_ready/0/"
offset = 5000
steps = 2000
header = TRUE
column_names = c("latitude", "longitude")
total_cuts = 20
real_data = TRUE
cut_data(dataset_dir, output_dir, offset, steps, header, column_names, total_cuts, real_data, NULL, NULL)

Read ants data Selected: 0,1,2,3,4

dataset_dir = paste(base_path, "real_life/Ant20exploration20trajectories/data/", sep = "")

output_dir = "real_ready/1/"
offset = 10000
steps = 2000
header = FALSE
column_names = c("V2", "V3")
total_cuts = 5
real_data = TRUE
cut_data(dataset_dir, output_dir, offset, steps, header, column_names, total_cuts, real_data, NULL, NULL)

Read shark data Select 0-4

dataset_dir = paste(base_path, "real_life/sharks/data/", sep = "")

output_dir = "real_ready/2/"
offset = 10000
steps = 2000
header = TRUE
column_names = c("lat", "long")
total_cuts = 5
real_data = TRUE
cut_data(dataset_dir, output_dir, offset, steps, header, column_names, total_cuts, real_data, NULL, NULL)
# dataset_name  = paste(dataset_dir, "BT_Palmyra_telemetry_hourly_through2015.csv", sep = "")
# df = read.csv(dataset_name, check.names = FALSE, header = header, stringsAsFactors = FALSE)
# 
# plot(df$lat[1:50], df$long[1:50], type = "l")

Read spiders data Data is divided in small trials…. Selected 0, 1, 6, 7, 14

dataset_dir = paste(base_path, "real_life/spiders/data/", sep = "")

output_dir = "real_ready/3/"
offset = 50000
steps = 2000
header = TRUE
column_names = c("x location mm", "y location mm")
total_cuts = 15
real_data = TRUE
cut_data(dataset_dir, output_dir, offset, steps, header, column_names, total_cuts, real_data, NULL, NULL)

Read jaguar data Select 0, 2, 3, 5, 6

dataset_dir = paste(base_path, "real_life/jaguars/data/", sep = "")

output_dir = "real_ready/4/"
offset = 5000
steps = 2000
header = TRUE
column_names = c("location.long", "location.lat")
total_cuts = 10
real_data = TRUE
cut_data(dataset_dir, output_dir, offset, steps, header, column_names, total_cuts, real_data, NULL, NULL)

Read boids data

dataset_dir = paste(base_path, "fake_life/boids", sep = "")
output_dir = "fake_ready/0/"
offset = 0
steps = 2000
header = FALSE
column_names = c("V2", "V3")
total_cuts = 5
real_data = FALSE
diffmax = c(0.4,0.4) #
field_size = c(1,1)
cut_data(dataset_dir, output_dir, offset, steps, header, column_names, total_cuts, real_data, diffmax, field_size)

Clean artificial chemistry data Data is already perfectly clean

dataset_dir = paste(base_path, "fake_life/artificial_chemistry/", sep = "")
output_dir = "fake_ready/1/"
offset = 0
steps = 2000
header = FALSE
column_names = c("V2", "V3")
total_cuts = 5
real_data = TRUE # no cleaning needed
diffmax = NULL
field_size = NULL
cut_data(dataset_dir, output_dir, offset, steps, header, column_names, total_cuts, real_data, diffmax, field_size)

Read Olaf data 1

dataset_dir = paste(base_path, "fake_life/olaf_1/", sep = "")
output_dir = "fake_ready/2/"
offset = 0
steps = 2000
header = TRUE
column_names = c("x", "y")
total_cuts = 5
diffmax = c(6,6)
field_size = c(8,8)
cut_data(dataset_dir, output_dir, offset, steps, header, column_names, total_cuts, FALSE, diffmax, field_size)

Read Olaf data 2 Data is clean

dataset_dir = paste(base_path, "fake_life/olaf_2/", sep = "")
output_dir = "fake_ready/3/"
offset = 0
steps = 2000
header = TRUE
column_names = c("x", "y")
total_cuts = 5
real_data = TRUE # no cleaning needed
diffmax = NULL
field_size = NULL
cut_data(dataset_dir, output_dir, offset, steps, header, column_names, total_cuts, real_data, diffmax, field_size)

Read robot arm data

dataset_dir = paste(base_path, "fake_life/robot_arm/", sep = "")
output_dir = "fake_ready/4/"
offset = 0
steps = 2000
header = TRUE
column_names = c("x", "y")
total_cuts = 5
real_data = TRUE # no cleaning needed
diffmax = NULL
field_size = NULL
cut_data(dataset_dir, output_dir, offset, steps, header, column_names, total_cuts, real_data, diffmax, field_size)

Finally, plot all selected data

dataset_dir = paste(base_path, "real_ready/", sep = "")
all_files = list.files(path = dataset_dir, full.names = TRUE, recursive = TRUE)
for(dataset_name in all_files){
    df = read.csv(dataset_name, check.names = FALSE, header = header, stringsAsFactors = FALSE)
    plot(x = df$x, y = df$y, type = "l", main = dataset_name)
}

dataset_dir = paste(base_path, "fake_ready/", sep = "")
all_files = list.files(path = dataset_dir, full.names = TRUE, recursive = TRUE)
for(dataset_name in all_files){
    df = read.csv(dataset_name, check.names = FALSE, header = header, stringsAsFactors = FALSE)
    plot(x = df$x, y = df$y, type = "l", main = dataset_name)
}